Triple

T16728730
Position Surface form Disambiguated ID Type / Status
Subject Sōtō Zen E406529 entity
Predicate headTemple P652 FINISHED
Object Sōjiji
Sōjiji is one of the two main head temples of the Sōtō school of Zen Buddhism in Japan, serving as a major center for monastic training and religious administration.
 E1237352 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sōjiji | Statement: [Sōtō Zen, headTemple, Sōjiji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sōjiji
Context triple: [Sōtō Zen, headTemple, Sōjiji]
  • A. Gyōda
    Gyōda is a city in Saitama Prefecture, Japan, known for its historic Oshi Castle and well-preserved traditional townscape.
  • B. Shōgen
    Shōgen was a short Japanese era of the late 13th century during the reign of Emperor Kameyama.
  • C. Gyōki
    Gyōki was an influential Japanese Buddhist monk of the Nara period known for his public works, social welfare activities, and role in promoting Buddhism among the common people.
  • D. Shōren-in
    Shōren-in is a historic Tendai Buddhist temple in Kyoto, Japan, known for its elegant gardens, traditional architecture, and role as a former residence of imperial priests.
  • E. Honen-in
    Honen-in is a tranquil, moss-covered Buddhist temple in Kyoto known for its serene gardens and understated, contemplative atmosphere.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sōjiji
Triple: [Sōtō Zen, headTemple, Sōjiji]
Generated description
Sōjiji is one of the two main head temples of the Sōtō school of Zen Buddhism in Japan, serving as a major center for monastic training and religious administration.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sōjiji
Target entity description: Sōjiji is one of the two main head temples of the Sōtō school of Zen Buddhism in Japan, serving as a major center for monastic training and religious administration.
  • A. Gyōda
    Gyōda is a city in Saitama Prefecture, Japan, known for its historic Oshi Castle and well-preserved traditional townscape.
  • B. Shōgen
    Shōgen was a short Japanese era of the late 13th century during the reign of Emperor Kameyama.
  • C. Gyōki
    Gyōki was an influential Japanese Buddhist monk of the Nara period known for his public works, social welfare activities, and role in promoting Buddhism among the common people.
  • D. Shōren-in
    Shōren-in is a historic Tendai Buddhist temple in Kyoto, Japan, known for its elegant gardens, traditional architecture, and role as a former residence of imperial priests.
  • E. Honen-in
    Honen-in is a tranquil, moss-covered Buddhist temple in Kyoto known for its serene gardens and understated, contemplative atmosphere.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8838f242881908abd8bc138795886 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e38749baa48190892b2e2b978f6eb6 completed April 18, 2026, 1:29 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb04c1e88190b6c9f43fbdfd6bc4 completed May 10, 2026, 5:06 p.m.
NEDg Description generation batch_6a00bf01716481908c50ee3d439909e5 completed May 10, 2026, 5:23 p.m.
NED2 Entity disambiguation (via description) batch_6a00bf760a488190b918fbd56f706035 completed May 10, 2026, 5:25 p.m.
Created at: April 10, 2026, 5:20 a.m.